Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LLM-Coding/Semantic-Anchors --skill arc42-documentationgit clone --depth 1 https://github.com/LLM-Coding/Semantic-AnchorsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/llm-coding/semantic-anchors/arc42-documentation)<a href="https://agentmods.dev/skills/llm-coding/semantic-anchors/arc42-documentation"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/arc42-documentation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/llm-coding/semantic-anchors/arc42-documentation"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/arc42-documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00139 | $0.01326 |
| Opus 5.5 | $0.00056 | $0.00530 |
| Sonnet 5.5 | $0.00028 | $0.00265 |
| Haiku 4.5 | $0.00014 | $0.00133 |
Grade A, and why
arc42-documentation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arc42 Documentation Authoring
Produce an arc42 architecture document that holds together across sections — not twelve chapters written in isolation.
When to use this skill
Use it when you are creating a new arc42 document, filling empty chapters, or auditing an existing one against the project's rules. The architecture-documentation contract names what the project means by architecture documentation (arc42; C4 via PlantUML; Nygard ADRs with a 3-point Pugh matrix; six-part Quality Attribute Scenarios). This skill is the how — the procedure and the cross-section rules arc42's own templates do not enforce. Load it on demand; it is not always-on.
If you are recovering documentation from existing code rather than authoring it forward, use the socratic-code-theory-recovery skill instead — its Phase 2 synthesizes an arc42 document and applies the same rules defined here.
Step 1 — Scaffold, do not restate
Scaffold the arc42 "with-help" template into the project's src/docs/ via docToolchain downloadTemplate. Each chapter's help text is its own structural spec; the process fills the help text and then replaces it. Do not paste a chapter skeleton from memory — let the template carry the structure so it stays current with arc42.
Step 2 — Diagrams
Every context, building-block, and runtime chapter carries at least one diagram. Diagrams are PlantUML, not Mermaid. Building blocks use C4 via PlantUML's bundled C4-PlantUML standard library — the !include <C4/...> stdlib form (angle brackets), never the remote https:// URL and never a vendored file copy. Diagrams are concrete components, not generic boxes.
Step 3 — Decisions (ADRs)
Decisions are ADRs in Nygard format with a 3-point Pugh matrix (-1 / 0 / +1).
- When the rationale is unconfirmed, set ADR Status to "Accepted (inferred)" and mark Pugh cells that need team judgement with
?rather than guessing a number. - Each ADR's Consequences name the risks the decision creates, referencing the Chapter 11 risk IDs (R-NNN). A decision that creates a risk not yet in Chapter 11 either adds it there or records the consequence as explicitly accepted without a tracked risk.
- Conversely, every Chapter 8 crosscutting concept back-references the ADR that decided it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +8 lines · +139 tokens per session 72689678bd5a
- 2mo ago First seen · 73 lines · 0 tokens per session scan A 55b3c23200d2
arc42-documentation is a skill published in the GitHub repository LLM-Coding/Semantic-Anchors (528 stars, last pushed today), licensed Apache-2.0. It adds 139 tokens to every session and 1,326 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.
pixel-art-studio
A toolkit and workflow for creating pixel art, which is digital artwork made from deliberately placed, visible pixels. It supports static sprites, animations, sprite sheets, image conversion, palettes, and quality checks.
deep-review
Parallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency, error-handling, frontend, testing), each with a focused checklist and isolated context. Synthesizes findings into unified report with FIX/DEFER/ACCEPT triage. Use…